Neural Message Passing for Multi-Label Classification
By Jack Lanchantin, Arshdeep Sekhon, Yanjun Qi. 2019
41 citations recorded by the source corpus.
Multi-label classification (MLC) is the task of assigning a set of target labels for a given sample. Modeling the combinatorial label interactions in MLC has been a long-haul challenge. We propose Label Message Passing (LaMP) Neural Networks to efficiently model the joint prediction of multiple labels. LaMP treats labels as nodes on a label-interaction graph and computes the hidden representation of each label node conditioned on the input using attention-based neural message passing. Attention enables LaMP to assign different importance to neighbor nodes per label, learning how labels interact (implicitly). The proposed models are simple, accurate, interpretable, structure-agnostic, and applicable for predicting dense labels since LaMP is incredibly parallelizable. We validate the benefits of LaMP on seven real-world MLC datasets, covering a broad spectrum of input/output types and outperforming the state-of-the-art results. Notably, LaMP enables intuitive interpretation of how classifying each label depends on the elements of a sample and at the same time rely on its interaction with other labels. We provide our code and datasets at this https URL
Subfields: Artificial Intelligence, Natural Language Processing, Graph Learning, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Quoc V. Le
- Mohit Bansal
- Yonghui Wu
- Ruoming Pang
- Yonatan Belinkov
- Luke S. Zettlemoyer
- Yoshua Bengio
- Vicente Ordonez
In Natural Language Processing
- Vicente Ordonez
- Tianlu Wang
- Yonghui Wu
- Ruoming Pang
- Yanjun Qi
- Michael Isard
- Aakanksha Chowdhery
- Jack Lanchantin
In Signal Processing
- Ruoming Pang
- Yonghui Wu
- Yanjun Qi
- Vicente Ordonez
- Michael Isard
- Aakanksha Chowdhery
- Jack Lanchantin
- Joseph Dean
Citations in the corpus
- Pathways: Asynchronous Distributed Dataflow for ML (2022, background): “Nevertheless, batching is not a panacea: it puts pressure on the limited HBM memory capacity, and very large batch sizes can slow model convergence rates (Shallue et al., 2018; You et al., 2017; Lanchantin et al., 2020; Anil et al., 2021).”
- General Multi-label Image Classification with Transformers (2020, background): “(4) Label Graph Formulation: Several recent studies [9, 30, 8, 7] used graph neural networks to model label dependency an obtained state-of-the-art results.”